In article <local.mail.freebsd-current/[EMAIL PROTECTED]> you write:
>> In message <[EMAIL PROTECTED]>, Mike Smith writes:
>> >> fxp0: The Intel driver is by far the highest preformance model,
>> >> beats the 3com (second best) hands down with much lower CPU
>> >> overhead.
>> >
>> >Do you actually have any numbers to quantify this? There's nothing in
>> >the driver architecture nor any of my testing that would suggest this is
>> >actually the case at this point.
>>
>> The FreeBSD fxp driver does a lot to reduce the number of transmit
>> interrupts; only 1/120 of transmitted packets result in interrupts. See
>> the code relating to FXP_CXINT_THRESH.
>>
>> Assuming an even balance of transmitted and received packets, this should
>> reduce the total number of interrupts by nearly 50%. I don't know if
>> drivers for other cards do (or even can) use this approach.
>
>This is why I'm asking for real information here; so far all I'm hearing
>is folklore. The xl driver, for example, does both transmit and receive
>interrupt coalescing, which should make it superior again, right? 8(
I've found that fxp and xl are roughly on a par for cpu overhead
when under heavy http traffic, with xl holding a slight edge last
time I looked.
Of course, if you _really_ want to reduce cpu load, the Alteon cards
(and the ti driver) beat both of them.
--
Jonathan
To Unsubscribe: send mail to [EMAIL PROTECTED]
with "unsubscribe freebsd-current" in the body of the message
